Image region entropy: A measure of "visualness" of web images associated with one concept

Keiji Yanai, Jacobus J Barnard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

54 Citations (Scopus)

Abstract

We propose a new method to measure "visualness" of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power is important for image annotation, especially automatic image annotation by image recognition system, since not all concepts are related to visual contents. Our method performs probabilistic region selection for images which are labeled as concept "X" or "non-X", and computes an entropy measure which represents "visualness" of concepts. In the experiments, we collected about forty thousand images from the World-Wide Web using the Google Image Search for 150 concepts. We examined which concepts are suitable for annotation of image contents.

Original languageEnglish (US)
Title of host publicationProceedings of the 13th ACM International Conference on Multimedia, MM 2005
Pages419-422
Number of pages4
DOIs
StatePublished - 2005
Event13th ACM International Conference on Multimedia, MM 2005 - Singapore, Singapore
Duration: Nov 6 2005Nov 11 2005

Other

Other13th ACM International Conference on Multimedia, MM 2005
CountrySingapore
CitySingapore
Period11/6/0511/11/05

Fingerprint

Image recognition
World Wide Web
Entropy
Experiments

Keywords

  • Image annotation
  • Probabilistic image selection
  • Web image mining

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Software

Cite this

Yanai, K., & Barnard, J. J. (2005). Image region entropy: A measure of "visualness" of web images associated with one concept. In Proceedings of the 13th ACM International Conference on Multimedia, MM 2005 (pp. 419-422) https://doi.org/10.1145/1101149.1101241

Image region entropy : A measure of "visualness" of web images associated with one concept. / Yanai, Keiji; Barnard, Jacobus J.

Proceedings of the 13th ACM International Conference on Multimedia, MM 2005. 2005. p. 419-422.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yanai, K & Barnard, JJ 2005, Image region entropy: A measure of "visualness" of web images associated with one concept. in Proceedings of the 13th ACM International Conference on Multimedia, MM 2005. pp. 419-422, 13th ACM International Conference on Multimedia, MM 2005, Singapore, Singapore, 11/6/05. https://doi.org/10.1145/1101149.1101241
Yanai K, Barnard JJ. Image region entropy: A measure of "visualness" of web images associated with one concept. In Proceedings of the 13th ACM International Conference on Multimedia, MM 2005. 2005. p. 419-422 https://doi.org/10.1145/1101149.1101241
Yanai, Keiji ; Barnard, Jacobus J. / Image region entropy : A measure of "visualness" of web images associated with one concept. Proceedings of the 13th ACM International Conference on Multimedia, MM 2005. 2005. pp. 419-422
@inproceedings{156dc16797254ea4918cb53569d09055,
title = "Image region entropy: A measure of {"}visualness{"} of web images associated with one concept",
abstract = "We propose a new method to measure {"}visualness{"} of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power is important for image annotation, especially automatic image annotation by image recognition system, since not all concepts are related to visual contents. Our method performs probabilistic region selection for images which are labeled as concept {"}X{"} or {"}non-X{"}, and computes an entropy measure which represents {"}visualness{"} of concepts. In the experiments, we collected about forty thousand images from the World-Wide Web using the Google Image Search for 150 concepts. We examined which concepts are suitable for annotation of image contents.",
keywords = "Image annotation, Probabilistic image selection, Web image mining",
author = "Keiji Yanai and Barnard, {Jacobus J}",
year = "2005",
doi = "10.1145/1101149.1101241",
language = "English (US)",
isbn = "1595930442",
pages = "419--422",
booktitle = "Proceedings of the 13th ACM International Conference on Multimedia, MM 2005",

}

TY - GEN

T1 - Image region entropy

T2 - A measure of "visualness" of web images associated with one concept

AU - Yanai, Keiji

AU - Barnard, Jacobus J

PY - 2005

Y1 - 2005

N2 - We propose a new method to measure "visualness" of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power is important for image annotation, especially automatic image annotation by image recognition system, since not all concepts are related to visual contents. Our method performs probabilistic region selection for images which are labeled as concept "X" or "non-X", and computes an entropy measure which represents "visualness" of concepts. In the experiments, we collected about forty thousand images from the World-Wide Web using the Google Image Search for 150 concepts. We examined which concepts are suitable for annotation of image contents.

AB - We propose a new method to measure "visualness" of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power is important for image annotation, especially automatic image annotation by image recognition system, since not all concepts are related to visual contents. Our method performs probabilistic region selection for images which are labeled as concept "X" or "non-X", and computes an entropy measure which represents "visualness" of concepts. In the experiments, we collected about forty thousand images from the World-Wide Web using the Google Image Search for 150 concepts. We examined which concepts are suitable for annotation of image contents.

KW - Image annotation

KW - Probabilistic image selection

KW - Web image mining

UR - http://www.scopus.com/inward/record.url?scp=36849034452&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36849034452&partnerID=8YFLogxK

U2 - 10.1145/1101149.1101241

DO - 10.1145/1101149.1101241

M3 - Conference contribution

AN - SCOPUS:36849034452

SN - 1595930442

SN - 9781595930446

SP - 419

EP - 422

BT - Proceedings of the 13th ACM International Conference on Multimedia, MM 2005

ER -